# Import necessary packages
import os
import scanpy as sc
import numpy as np
import pandas as pd
import anndata as ad
from datetime import datetime as dt

# Scanpy settings
sc.settings.verbosity = 3
sc.logging.print_header()

# Set working directory
os.chdir("/home/dalbao/2023-012-Runx3mutD8scRNA/AlbaoRunx3Manuscript/single_cell/02_optimization")

adata = "01_25-12-05-17-25_preprocessing_MRE.h5ad"

2025-12-05 22:27:57.336510: I tensorflow/core/platform/cpu_feature_guard.cc:182] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations.
To enable the following instructions: SSE4.1 SSE4.2 AVX AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags.

scanpy==1.9.5 anndata==0.10.2 umap==0.5.4 numpy==1.24.4 scipy==1.11.3 pandas==2.1.1 scikit-learn==1.3.1 statsmodels==0.14.0 igraph==0.11.2 louvain==0.8.1 pynndescent==0.5.10

# Determine work location
print("The work location for this notebook is: " + os.getcwd() + "\n")

# Get a timestamp for the start of the run
timestamp = dt.now()
print("This notebook was last run on " + timestamp.strftime("%y-%m-%d %H:%M") + "\n")

The work location for this notebook is: /blue/m.pipkin/dalbao/2023-012-Runx3mutD8scRNA/AlbaoRunx3Manuscript/single_cell/02_optimization

This notebook was last run on 25-12-05 22:28

# List items in outs folder
adata = ad.read_h5ad("../../h5ad/" + adata)

# Inspect AnnData
print(adata)

AnnData object with n_obs × n_vars = 28407 × 18505
    obs: 'experiment', 'group', 'timepoint', 'infection', 'cell_id', 'n_genes_by_counts', 'log1p_n_genes_by_counts', 'total_counts', 'log1p_total_counts', 'total_counts_mt', 'log1p_total_counts_mt', 'pct_counts_mt', 'total_counts_ribo', 'log1p_total_counts_ribo', 'pct_counts_ribo', 'doublet_score', 'predicted_doublet', 'scDblFinder_score', 'scDblFinder_class', 'gem', 'QC', 'n_genes', 'S_score', 'G2M_score', 'phase'
    var: 'mt', 'ribo', 'n_cells_by_counts-gem1', 'mean_counts-gem1', 'log1p_mean_counts-gem1', 'pct_dropout_by_counts-gem1', 'total_counts-gem1', 'log1p_total_counts-gem1', 'n_cells_by_counts-gem2', 'mean_counts-gem2', 'log1p_mean_counts-gem2', 'pct_dropout_by_counts-gem2', 'total_counts-gem2', 'log1p_total_counts-gem2', 'n_cells', 'n_counts', 'highly_variable', 'means', 'dispersions', 'dispersions_norm', 'mean', 'std'
    uns: 'group_colors', 'hvg', 'log1p', 'pca'
    obsm: 'X_pca'
    varm: 'PCs'
    layers: 'counts', 'soupX_counts'

# Define a function to automate the iteration of different neighbor values, holding PC constant.
def iterate_neighbors(adata_local, pcs = 25, neighbors = 10, min = 0, max = 11):
    # Loop over different nearest neighbor values based on provided min and max values
    for index in range(min, max):
        # Calculate nearest neighbors with n_neighbors of neighbors + index
        adata_mod = sc.pp.neighbors(adata_local, n_neighbors = neighbors + index, n_pcs = pcs, copy = True)
        
        # Do leiden clustering from neighborhood graph
        sc.tl.leiden(adata_mod)
        
        # Initialize the PAGA
        sc.tl.paga(adata_mod)
        sc.pl.paga(adata_mod, title = "neighbor " + str(neighbors + index) + " pcs " + str(pcs))

        # Do a UMAP based on initialized PAGA graph
        sc.tl.umap(adata_mod, init_pos='paga')

        # Plot UMAP annotated by leiden clusters and original identity
        sc.pl.umap(adata_mod, color = "group", title = "neighbor " + str(neighbors + index) + " pcs " + str(pcs))
        sc.pl.umap(adata_mod, color = "leiden", title = "neighbor " + str(neighbors + index) + " pcs " + str(pcs))

        # Get leiden clusters and original identities
        obs_df = sc.get.obs_df(adata_mod, ["group", "leiden"])
        # Print tapply
        print(obs_df.groupby("group").value_counts().unstack())

        del(adata_mod) # Cleanup
        
    # End of loop
    
    del(adata_local)
            
# End of function

iterate_neighbors(adata, pcs = 25, neighbors = 3, min = 0, max = 18)

computing neighbors
    using 'X_pca' with n_pcs = 25
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:20)
running Leiden clustering
    finished: found 51 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:02)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:02)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:05)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

leiden     0     1     2    3    4    5    6    7    8    9  ...  41  42  43  \
group                                                        ...               
Base       6     1     6   20  377  393   20  523  119  528  ...  26   2   0   
Naive      0     0     0    0    0    0    0    0    0    0  ...   0   0   0   
Null       0     0    23    1  357  283   47  282  618  339  ...  18   5   0   
WT        25  1545    33  136   46   71   21   82   46   35  ...  16   0   0   
d5         3     2     2    1   23   19    6    4    2    6  ...   1   0  19   
d8         6     0     0    5  242   95    7   51   64   84  ...   1   0   0   
dAD        8     0  1315   45   46   94  902   63  123   29  ...  13  24   0   
dID     1679     9    17   33   62   75   28   47   73   42  ...  13   3   5   
dVWRPY    17    42    67  979   37   74   61   38   40   20  ...   5   0   0   

leiden  44  45  46  47  48  49  50  
group                               
Base     0   0   0   0   1   0   0  
Naive    0   0   0   0   0   3   0  
Null     0   0   0   1   2   0   2  
WT       0   0   1   0   0   0   0  
d5       0   6   0   0   0   0   0  
d8       0   0   0   0   0   0   0  
dAD     17   0   0   2   0   0   1  
dID      0   0   0   0   0   0   0  
dVWRPY   1   1   3   1   0   0   0  

[9 rows x 51 columns]
computing neighbors

/scratch/local/20367146/ipykernel_1275877/2632075354.py:25: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  print(obs_df.groupby("group").value_counts().unstack())

    using 'X_pca' with n_pcs = 25
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:03)
running Leiden clustering
    finished: found 25 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:03)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:01)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:07)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

iterate_neighbors(adata, pcs = 30, neighbors = 3, min = 0, max = 18)

computing neighbors
    using 'X_pca' with n_pcs = 30
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:02)
running Leiden clustering
    finished: found 48 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:07)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:02)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:07)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

leiden     0     1    2     3     4    5    6     7    8    9  ...  38  39  \
group                                                          ...           
Base       7     2  588    20     5  429   14     5  318   19  ...   1  33   
Naive      0     0    0     0     0    1    0     0    0    0  ...   1   0   
Null      19     1  576     2     1  295    9     0  310   29  ...  11   7   
WT        26  1622   99    27   171  105  206  1024   61   21  ...   7   7   
d5         1     7   23     4     6   42   14     2   16    3  ...  20   3   
d8         1     0   88    10     0   95   16     0  240    1  ...  12   3   
dAD     1914     0   67     2    30   83   57     0   39  787  ...  12   2   
dID        8    18   84  1409    41   98   57    26   66   21  ...  11  28   
dVWRPY    68    95   43    20  1137   71  755    44   27   42  ...  15   4   

leiden  40  41  42  43  44  45  46  47  
group                                   
Base    17   1   0   0   3   3   0   0  
Naive    0   0   0   0   0   0   3   0  
Null    12   1   0   0   0   0   0   2  
WT      17   2   0   0   1   0   0   0  
d5       0   0   8   7   0   0   0   0  
d8       1   0   0   0   0   0   0   0  
dAD     10   0   0   0   0   0   0   0  
dID     15   0   0   0   0   0   0   1  
dVWRPY   6   4   0   1   0   0   0   0  

[9 rows x 48 columns]
computing neighbors

/scratch/local/20367146/ipykernel_1275877/2632075354.py:25: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  print(obs_df.groupby("group").value_counts().unstack())

    using 'X_pca' with n_pcs = 30
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:03)
running Leiden clustering
    finished: found 26 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:02)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:01)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:07)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

iterate_neighbors(adata, pcs = 35, neighbors = 3, min = 0, max = 18)

computing neighbors
    using 'X_pca' with n_pcs = 35
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:02)
running Leiden clustering
    finished: found 48 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:02)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:02)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:05)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

leiden     0     1    2     3    4    5     6     7    8    9  ...  38  39  \
group                                                          ...           
Base       8     8   25    12  198  436     5     0  244  405  ...   3  44   
Naive      0     0    0     0    0    0     0     0    0    0  ...   1   0   
Null       3    29    4     0  677  481    40     0  563  263  ...  11   7   
WT        37    25  156  1052   43   56    27  1127   38   45  ...   8   7   
d5         2     0    6     0    2    5     2     0    6   19  ...  32  10   
d8        13     0    6     4   91   40     0     0   82  248  ...  11   8   
dAD        4  1317   76     4   98   61  1041     0   93   44  ...  13   3   
dID     1592    14   51    34   59   56    19     2   74   60  ...  10   3   
dVWRPY    34    65  928   102   22   42    43     9   34   28  ...  16   2   

leiden  40  41  42  43  44  45  46  47  
group                                   
Base     0   0   0   0   0   0   0   0  
Naive    0   0   0   0   3   0   0   0  
Null     0   0   4   0   0   0   0   0  
WT       0   0   0   0   0   1   0   0  
d5      81   7   0   4   0   0   0   1  
d8       0   0   0   0   0   0   0   1  
dAD      0   0   0   0   0   0   0   0  
dID      0   0   0   0   0   1   0   1  
dVWRPY   0   1   0   0   0   1   3   0  

[9 rows x 48 columns]
computing neighbors

/scratch/local/20367146/ipykernel_1275877/2632075354.py:25: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  print(obs_df.groupby("group").value_counts().unstack())

    using 'X_pca' with n_pcs = 35
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:02)
running Leiden clustering
    finished: found 24 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:02)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:01)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:06)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

iterate_neighbors(adata, pcs = 40, neighbors = 3, min = 0, max = 18)

computing neighbors
    using 'X_pca' with n_pcs = 40
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:02)
running Leiden clustering
    finished: found 51 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:01)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:02)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:05)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

leiden     0     1     2     3     4     5    6    7     8    9  ...  41  42  \
group                                                            ...           
Base      13    10     2    11    15    15  180  444    10  412  ...   0   7   
Naive      0     0     0     0     0     0    0    0     0    0  ...   0   0   
Null      40     4     0     0    21     6  688  510     4  221  ...   0   4   
WT        29   250  1410  1088    20    47   56   57    20   62  ...   0  29   
d5         2    10     6     3     1     8    4    5     5   12  ...  93   0   
d8         3     3     1     2     2     9   52   32     9  244  ...   0   1   
dAD     1415    30     0     6  1126     7  120   54     5   39  ...   0   8   
dID       22    29     5    32    11  1121   87   38  1001   34  ...   0  19   
dVWRPY    57  1197    49   125    38    18   35   25    25   32  ...   1   9   

leiden  43  44  45  46  47  48  49  50  
group                                   
Base    38   0   1   2   0   0   0   0  
Naive    0   0   0   0   0   3   0   0  
Null    19   0   0   6   0   0   0   0  
WT       4   0  11   0   0   0   0   0  
d5       2  23   0   0   7   0   0   0  
d8       1   0   0   0   0   0   0   0  
dAD      4   0   0   0   0   0   0   0  
dID      4   0   0   1   0   0   3   3  
dVWRPY   4   0   4   0   1   0   0   0  

[9 rows x 51 columns]
computing neighbors

/scratch/local/20367146/ipykernel_1275877/2632075354.py:25: FutureWarning: The default of observed=False is deprecated and will be changed to True in a future version of pandas. Pass observed=False to retain current behavior or observed=True to adopt the future default and silence this warning.
  print(obs_df.groupby("group").value_counts().unstack())

    using 'X_pca' with n_pcs = 40
    finished: added to `.uns['neighbors']`
    `.obsp['distances']`, distances for each pair of neighbors
    `.obsp['connectivities']`, weighted adjacency matrix (0:00:02)
running Leiden clustering
    finished: found 28 clusters and added
    'leiden', the cluster labels (adata.obs, categorical) (0:00:01)
running PAGA
    finished: added
    'paga/connectivities', connectivities adjacency (adata.uns)
    'paga/connectivities_tree', connectivities subtree (adata.uns) (0:00:01)
--> added 'pos', the PAGA positions (adata.uns['paga'])

computing UMAP
    finished: added
    'X_umap', UMAP coordinates (adata.obsm) (0:00:06)

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1207: FutureWarning: is_categorical_dtype is deprecated and will be removed in a future version. Use isinstance(dtype, CategoricalDtype) instead
  if not is_categorical_dtype(values):
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:1216: FutureWarning: The default value of 'ignore' for the `na_action` parameter in pandas.Categorical.map is deprecated and will be changed to 'None' in a future version. Please set na_action to the desired value to avoid seeing this warning
  color_vector = pd.Categorical(values.map(color_map))
/opt/conda/lib/python3.10/site-packages/scanpy/plotting/_tools/scatterplots.py:391: UserWarning: No data for colormapping provided via 'c'. Parameters 'cmap' will be ignored
  cax = scatter(

# End of Notebook
print("\nNotebook Ends")

Notebook Ends

Neighbor Optimization MRE¶

Initialize Environment¶

Optimize Nearest Neighbors¶

25 PCs, neigbhor 3 to 18¶

30 PCs, neigbhor 3 to 18¶

35 PCs, neigbhor 3 to 18¶

40 PCs, neigbhor 3 to 18¶